apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-07-11 16:22:10 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add a risk score to the base class DatasetAttackScore, so that every implementation could set it based on its specific values.

Browse source 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
This commit is contained in:
Maya Anderson 2023-03-16 17:51:49 +02:00
parent 8a4df5a4a2
commit 80bec0c45b
7 changed files with 53 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

4
apt/risk/data_assessment/attack_strategy_utils.py
View file

@ -39,8 +39,8 @@ class KNNAttackStrategyUtils(AttackStrategyUtils):
:param query_samples: query samples, to which nearest neighbors are to be found
:param knn_learner: unsupervised learner for implementing neighbor searches, after it was fitted
:param distance_processor: function for processing the distance into another more relevant metric per sample.
Its input is an array representing distances (the distances returned by NearestNeighbors.kneighbors() ),
and the output should be another array with distance-based values that enable to compute the final score
Its input is an array representing distances (the distances returned by NearestNeighbors.kneighbors() ), and
the output should be another array with distance-based values that enable to compute the final risk score
:return:
distances of the query samples to their nearest neighbors, or a metric based on that distance and calculated
by the distance_processor function